Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/openshift-eng/ai-helpers/generate-dashboardgit clone --depth 1 https://github.com/openshift-eng/ai-helpersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/openshift-eng/ai-helpers/generate-dashboard)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/generate-dashboard"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/generate-dashboard.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00013 | $0.05363 |
| Opus 5 | $0.00006 | $0.02681 |
| Sonnet 5 | $0.00003 | $0.01073 |
| Haiku 4.5 | $0.00001 | $0.00536 |
Grade A, and why
generate-dashboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
operator-dashboard:generate-dashboard
Synopsis
/operator-dashboard:generate-dashboard <operator-name> [--namespace <ns>] [--output-dir <dir>]
Description
This command adds a new operator to an OpenShift Console dynamic plugin. It discovers the operator's CRDs via cluster API (e.g. oc api-resources), then generates the dashboard page, one table component per resource kind using the shared ResourceTable pattern, operator CSS, and extends ResourceInspect for the detail view. Optional parameters allow scoping to a namespace and writing output to a custom directory. The template components in skills/dashboard-templates/ define the CRD models (.ts) and list/detail UI components (ResourceTable, ResourceInspect) that are adapted to the target operator's API group, version, kind, and printer columns.
Implementation
Before starting, read the skill at
skills/dashboard-templates/SKILL.md. It documents every template component, explains when to use each one, and describes the patterns to follow when adapting them to a new operator's CRDs.
CRITICAL: What NOT to Do
Before implementing, review these common mistakes that break dashboard quality:
Button & Actions:
- ❌ DO NOT create inline
ResourceTableRowActionscomponents in table files - ❌ DO NOT use plain
<button>tags — use PatternFly<Button>component - ❌ DO NOT put
classNameon<Link>wrapper — put it on<Button> - ❌ DO NOT add custom background-color/border-color CSS for buttons
- ❌ DO NOT call
useDeleteModalinside.map()loops - ❌ DO NOT forget the Delete button — users need to delete resources!
- ✅ DO use
<Button variant="primary">for Inspect (blue) - ✅ DO use
<Button variant="danger">for Delete (red) - ✅ DO import and use shared
ResourceTableRowActionsfrom./ResourceTable
PatternFly 6 APIs:
- ❌ DO NOT use old CSS variable format
--pf-v6-global--* - ❌ DO NOT use old EmptyState API with child
<Title>component - ❌ DO NOT use
date={new Date(...)}with Timestamp - ❌ DO NOT use
variantprop for Label status colors - ✅ DO use token variables
--pf-t--global--*(PatternFly 6 semantic tokens) - ✅ DO use EmptyState props:
titleText,icon={SearchIcon},headingLevel - ✅ DO use
timestamp={resource.metadata?.creationTimestamp}with Timestamp - ✅ DO use Label
statusprop:status="success|danger|warning"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 395 lines · 13 tokens per session scan A 96986d2f256e
generate-dashboard is a command published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 5,363 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.